Yes, you can have Claude write NLP++ for you — and no, that doesn’t make it another black box. This step-by-step guide takes you from a blank machine to a working analyzer: install VS Code, add the NLP++ extension, run Claude Code, and use the built-in prompts to generate real, glass-box code. What you keep is deterministic, auditable, and runs on its own — no model required.
I spent the last 8 weeks using Claude to eventually replace Claude. Ironic…
Read more
One of the strengths of NLP++ is that once you’ve written an analyzer in the VisualText VS Code extension, you are not locked into a single way of running it. The same glass-box, 100% rule-based analyzer can be driven from Python, from Node.js, from TypeScript, or straight from the command […]
Read more
For most of its life, the NLP++ engine has been a powerful tool for writing rule-based analyzers — explainable, glass-box, and deterministic natural-language processing you can actually read, debug, and reproduce exactly. It has run on Windows, Linux, and macOS for years. What Version 3 changes is how you build, […]
Read more
Compiling NLP++ analyzers is now a single click. Version 3 brings native-code speed and lets you deploy analyzers without exposing your source.
Read more
LLMs guess. NLP++ understands. And that difference is exactly why NLP++ is the only technology positioned to eventually replace large language models in real‑world text processing. LLMs are probabilistic black boxes. They don’t know anything; they predict. They require teaming — layers of prompts, validators, guardrails, and secondary models — […]
Read more
With our NLP++ textbook coming out world-wide this month (it may be already out by the time you read this), people are asking: what is the difference between LLMs and NLP++? Here is a first attempt of mine to explain. NLP++ and LLMs aren’t two approaches to the same problem. […]
Our neural network brains are bamboozled by the “average”, but we “average” people are waking up. This explains why we are so easily fooled and how human ingenuity can get us out of this (A)verage (I)ndustry mess.
In recent comment threads and after reading the ubiquitous posts on “AI” on LinkedIn, I have come to the revelation that we are living in the “era of shallow thinking”. And it is this problem that is holding us back from doing more “profound” things in computer science.
NLP++ authors David de Hilster and Amnon Meyers will be conducting a virtual workshop on NLP, NLP++, and Compilers from December 18 – 20, 2024. Sign Up For Each Session Here are the three sessions and a link to sign up. YOU MUST SIGN UP FOR EACH SESSION SEPARATELY. The […]
The Computer Science & Engineering Department at RV University in India has come to a long-term formal agreement with the Natural Language Understanding Global Initiative to work on rule-based NLP. Lead by Dr. G Shobha, dean of the School of Computer Science and Engineering, and Dr. Merin Thomas, the school […]
Regex is ubiquitous in the programming world because of its usefulness as a rule-based text parsing language. Programmers find comfort in the idea of writing explicit, modifiable rules in order to parse text. This is in contrast with black-box statistical models, which cannot be modified when things go wrong – […]
I have been in computational linguistics for more than 40 years, and this is the first time I have been to the most important conference in our field: the annual Association of Computational Linguistics (ACL) Conference. As part of the registration process, I became a member for the first time […]
Trustworthy NLP systems must be rule and knowledge based given all statistical systems like large language models, machine learning, and neural networks are not. With the advent of large language models that can be queried about common knowledge, it is natural to use them to generate linguistic and world knowledge […]
